On the characterization of VBR MPEG streams

  • Authors:
  • Marwan Krunz;Satish K. Tripathi

  • Affiliations:
  • Department of ECE, University of Arizona, Tucson, AZ;Department of CS, University of Maryland, College Park, MD

  • Venue:
  • SIGMETRICS '97 Proceedings of the 1997 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
  • Year:
  • 1997

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a comprehensive model for variable-bit-rate MPEG video streams. This model captures the bit-rate variations at multiple time scales. Long-term variations are captured by incorporating scene changes, which are most noticeable in the fluctuations of I frames. The size of an I frame is modeled by the sum of two random components: a scene-related component and an AR(2) component that accounts for the fluctuations within a scene. Two random processes of i.i.d. rvs are used to model the sizes of P and B frames, respectively. The complete model is then obtained by intermixing the three sub-models according to a given GOP pattern. It is shown that the composite model exhibits long-range dependence (LRD) in the sense that its autocorrelation function is non-summable. The LRD behavior is caused by the repetitive GOP pattern which induces periodic cross-correlations between different types of frames. Using standard statistical methods, we successfully fit our model to several empirical video traces. We then study the queueing performance for video traffic at a statistical multiplexer. The results show that the model is sufficiently accurate in predicting the queueing performance for real video streams.